c++ - strtok_r 导致段错误

Question

这段代码是解析一个csv文件，但是会导致segmentation fault。我可以在这里看到类似的代码:Nested strtok function problem in C

它们看起来一样，但我的代码导致段错误。为什么？

#include <cstdlib>
#include <string.h>
#include <stdio.h>
#include <vector>

using namespace std;

struct inputTuple{
    int user, item, rating;
};

int main(void)
{
    char xdata[] = "1,88,0,874965758;1,2,1,876893171;1,99,1,878542960;";
    vector<inputTuple> input;

            int maxUser = 0, maxItem = 0;
        int user, item, rating;

        char *end_str;
        char *data_point = strtok_r(xdata, ";", &end_str);

        while(data_point != NULL) {
            char *end_attr;
            char *data_point_attr = strtok_r(data_point, ",", &end_attr);
            while(data_point_attr != NULL) {

                user = atoi(data_point_attr);
                data_point_attr = strtok_r(NULL, ",", &end_attr);
                item = atoi(data_point_attr);
                data_point_attr = strtok_r(NULL, ",", &end_attr);
                rating = atoi(data_point_attr);
                strtok_r(NULL, ",", &end_attr);
                input.push_back({user, item, rating});
                maxUser = max(maxUser, user);
                maxItem = max(maxItem, item);
                }
            data_point = strtok_r(NULL, ";", &end_str);
        }
    return 0;
}

Answer 1

您的内部循环不是必需的，而且对您的程序有害。

内层循环抽取3个token，然后继续，抽取第4个token但中间到达NULL，atoi传NULL : 段错误。

您只需要一个循环(尽管添加了 assert 语句以保持理智):

    while(data_point != NULL) {
        char *end_attr;
        char *data_point_attr = strtok_r(data_point, ",", &end_attr);

            user = atoi(data_point_attr);
            data_point_attr = strtok_r(NULL, ",", &end_attr);
            assert(data_point_attr != NULL);
            item = atoi(data_point_attr);
            data_point_attr = strtok_r(NULL, ",", &end_attr);
            assert(data_point_attr != NULL);
            rating = atoi(data_point_attr);
            strtok_r(NULL, ",", &end_attr);
            input.push_back({user, item, rating});
            maxUser = max(maxUser, user);
            maxItem = max(maxItem, item);

        data_point = strtok_r(NULL, ";", &end_str);
    }

更好的解决方案是使用真正的 C++ 解决方案来拆分字符串。